Average cost optimality of partially observed MDPs: contraction of nonlinear filters and existence of optimal solutions and approximations

Cites Work

Measure theory. Vol. I and II
Stability and uniform approximation of nonlinear filters using the Hilbert metric and application to particle filters
Real Analysis and Probability
Optimal Infinite-Horizon Undiscounted Control of Finite Probabilistic Systems
On Near Optimality of the Set of Finite-State Controllers for Average Cost POMDP
Incomplete information in Markovian decision models
Partially observable total-cost Markov decision processes with weakly continuous transition probabilities
Reduction of a Controlled Markov Model with Incomplete Data to a Problem with Complete Information in the Case of Borel State and Control Space
Optimal Plans for Dynamic Programming Problems
Controlled Markov Processes with Arbitrary Numerical Criteria
On the existence of stationary optimal policies for partially observed MDPs under the long-run average cost criterion
Dynamic programming for ergodic control with partial observations.
Finite approximations in discrete-time stochastic control. Quantized models and asymptotic optimality
Remarks on the existence of solutions to the average cost optimality equation in Markov decision processes
A further remark on dynamic programming for partially observed Markov processes
Average Cost Dynamic Programming Equations For Controlled Markov Chains With Partial Observations
Robustness to Incorrect System Models in Stochastic Control
Robustness to Incorrect Priors and Controlled Filter Stability in Partially Observed Stochastic Control
Robustness to Incorrect Priors in Partially Observed Stochastic Control
Exponential filter stability via Dobrushin's coefficient
Dynamic Programming for Ergodic Control of Markov Chains under Partial Observations: A Correction
Weak Feller property of non-linear filters
Long Run Control with Degenerate Observation
Title not available (Why is that?)
Convergence of Finite Memory Q Learning for POMDPs and Near Optimality of Learned Policies Under Filter Stability

This page was built for publication: Average cost optimality of partially observed MDPs: contraction of nonlinear filters and existence of optimal solutions and approximations

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6640586)